browser-use/browser-use
Open-source browser automation agent for LLMs, usable as a Python library, CLI, hosted cloud service, or MCP server exposing browser-control tools.
Awesome MCP › Browser Automation
browserbase/mcp-server-browserbase
Browserbase MCP Server is a project that enables large language models (LLMs) to control and interact with web browsers through the Model Context Protocol (MCP). MCP is an open protocol designed to facilitate seamless integration between LLM applications and external data sources or tools, allowing AI-powered applications to access the context they need for enhanced functionality. This server leverages Browserbase and Stagehand to provide cloud browser automation capabilities, enabling LLMs to perform tasks such as interacting with web pages, taking screenshots, executing JavaScript, and extracting structured data from web content. The project is divided into two main MCP implementations: Browserbase MCP and Stagehand MCP. Browserbase MCP focuses on browser automation, data extraction, console monitoring, screenshot capture, and web interaction, allowing LLMs to navigate, click, and fill forms within cloud browsers. Stagehand MCP offers atomic instructions for precise actions, supports multiple AI models including OpenAI's GPT-4 and Anthropic's Claude-3.7 Sonnet, and features a modular design for easy integration of new models. It also supports vision capabilities through annotated screenshots for handling complex Document Object Models (DOMs). Browserbase MCP Server is designed to empower developers building AI-powered IDEs, chat interfaces, or custom AI workflows by providing a standardized way to connect LLMs with web browser contexts. The project is open source and encourages community contributions, with additional support available through a Slack community. It also acknowledges the Playwright team for their contributions to browser automation frameworks and the Playwright MCP Server. Overall, Browserbase MCP Server is a powerful tool for enabling advanced web interaction and automation through LLMs using the Model Context Protocol, facilitating innovative AI applications that require dynamic web data and control.
https://github.com/browserbase/mcp-server-browserbase
Also in Browser Automation
unclecode/crawl4ai
Open-source async web crawler and scraper that converts websites into clean, LLM-ready Markdown for RAG pipelines and AI agents, with an official MCP server for AI assistants.
microsoft/playwright-mcp
Playwright MCP is an MCP server that enables LLMs to automate and interact with web browsers using structured accessibility snapshots for efficient and deterministic browser automation.
alibaba/page-agent
Page Agent is an in-page JavaScript GUI agent that enables natural language control of web interfaces, offering easy integration without browser extensions or headless browsers.
Skyvern-AI/skyvern
Skyvern automates browser-based workflows using large language models and computer vision, providing a robust and scalable web automation solution that integrates with the Model Context Protocol (MCP).
browser-use/browser-harness
MCP-compatible harness that lets coding agents drive a user's real, logged-in Chrome browser over the DevTools Protocol, writing new helper scripts as it works.
apify/actors-mcp-server
Apify MCP Server is an MCP protocol server implementation that enables AI assistants to interact with Apify Actors for data extraction, web scraping, and automation tasks through a standardized protocol.
firecrawl/firecrawl-mcp-server
Firecrawl MCP Server is an MCP server implementation that adds advanced web scraping, crawling, and search capabilities to LLM clients like Cursor and Claude, enabling enhanced data extraction and research functionalities.